高分辨率图像建筑物提取数据集制作

1. 目录结构

   /dataset/
   	xxxx.tif  # 原始图像
   	image-3000
   		0.tif # 切割后的tif
   		1.tif
   		........
   		xxx_0.json # 生成的json文件也放在该文件夹下
   		xxx_1.json
   		.......
   		xxx_0_json # 调用labelme_json_to_dataset 0.json 生成的0_json文件夹
   			img.png # 原始图片的png格式
   			info.yaml
   			label.png # 标签图片
   			label_names.txt 
   			label_viz.png
   		xxx_1_json
   		.......
   		0.png  # 将json文件夹中的label.png 提取出来
   		1.png 
   		.......
   		label_0.tif # 将上边的png标签文件转换为tif格式

   

2. 收集数据，高分辨率图像

   1. 无人机数据，航空数据等

3. 图像切割，像素大小该为多少？

   1. 本数据集平均像素大小(40000*50000) tif格式，LZW压缩方式压缩

   2. 要考虑计算机显卡，目标建筑无尽量不被切割等问题，本利使用3000*3000

      # data:2020-01-04
      # user:dean
      # desc:图像切割脚本
      import tifffile as tiff  # 也可使用pillow或opencv 但若图片过大时可能会出问题
      import os
      width = 1500*2   # 切割图像大小
      height = 1500*2  # 切割图像大小
      home = "/media/dean/Document/AI_dataset/DOM/"
      file_name = "裴庄村51-dom"
      image_dir = os.path.join(home,file_name)
      image = os.path.join(image_dir,file_name+".tif")
      target_dir = os.path.join(image_dir,"image-"+str(width))  # 切割后图片存储位置
      if not os.path.exists(target_dir):
          os.mkdir(target_dir)
      img = tiff.imread(image)  # 导入图片
      print("导入图片完成",img.shape) # 原始图片大小
      pic_width = img.shape[1]
      pic_height = img.shape[0]
      row_num = pic_width//width  # 纵向切割数量
      col_num = pic_height // height  # 横向切割数量
      print("开始进行切割，可切割总数为{}".format(col_num*row_num))
      for j in range(col_num):
          for i in range(row_num):
              num = j * row_num + i
              print("正在进行第{}张切割".format(num + 1))
              row = i * width
              row_end = row + width
              col = j * height
              col_end = col + height
              # print(col,col_end,row,row_end)
              cropped = img[col:col_end,row:row_end]
              name = "{}_{}.tif".format(file_name,num)
              image_path = os.path.join(target_dir,name)
              tiff.imsave(image_path, cropped)

4. 标注工具 labelme

   1. 使用label标注每张图片

      pip install labelme  # 安装labelme

   2. 每张图片标注后会生成对应name.json文件

      labelme_json_to_dataset xxx.json

      

      # data:2020-01-04
      # user:dean
      # desc:批量将json文件转为 label
      import os
      dir = r"I:\人工智能数据\DOM\裴庄村51-dom\image-3000"
      files = [os.path.join(dir,file) for file in os.listdir(dir) if file.endswith(".json")]
      for file in files:
          cmd = "labelme_json_to_dataset {}".format(file)
          print(cmd)
          os.system(cmd)

   3. 将所有的json/label.png 提取到统一文件夹

      # data:2020-01-04
      # user:dean
      # desc:将label文件夹中的laebl提取出来
      import tifffile as tiff
      from PIL import Image
      import os
      target_dir = r"/media/dean/Document/AI_dataset/DOM/裴庄村51-dom/image-3000"  # json_label 所在的文件夹
      files = [os.path.join(target_dir,file) for file in os.listdir(target_dir)]
      for i in files:
          if os.path.isdir(i):
              lables = os.listdir(i)
              for file in lables:
                  if file == "label.png":
                      image_path = os.path.join(i, "label.png")
                      imgae = Image.open(image_path)
                      parent_dir_name = os.path.basename(os.path.dirname(image_path))
                      new_name = "{}.png".format(parent_dir_name.split("_")[1])
                      imgae.save(os.path.join(target_dir,new_name))
                      print("第{}个文件夹".format(i))
                      break;

   4. 将所有的label.png转换为tif格式 并转换为单通道黑白照片

      # coding:utf-8
      # file: change_format.py
      # author: Dean
      # contact: 1028968939@qq.com
      # time: 2020/1/4 20:41
      # desc: 将png 标签转化为单通道 黑白标签 并转化为tif
      import os
      from PIL import Image
      threshold = 0
      table = []
      for i in range(256):
          if i > threshold:
              table.append(255)
          else:
              table.append(0)
      target_dir = r"/media/dean/Document/AI_dataset/DOM/裴庄村51-dom/image-3000"
      files = [os.path.join(target_dir,file) for file in os.listdir(target_dir) if file.endswith(".png")]
      for file in files:
          image_file_name = os.path.basename(file)
          num = image_file_name.split(".")[0]
          image_file = Image.open(file)  # open colour image
          # image_file = image_file.convert('L') # convert image to black and white
          image_file = image_file.point(table, '1')
          new_file = os.path.join(target_dir,"{}.tif".format(num))
          image_file.save(new_file)
          print(new_file)

   5. 结束(根据需要提取相应数据即可)